Towards the prediction of renewable energy unbalance in smart grids

The production of renewable energy is increasing worldwide. To integrate renewable sources in electrical smart grids able to adapt to changes in power usage in heterogeneous local zones, it is necessary to accurately predict the power production that can be achieved from renewable energy sources. By using such predictions, it is possible to plan the power production from non-renewable energy plants to properly allocate the produced power and compensate possible unbalances. In particular, it is important to predict the unbalance between the power produced and the actual power intake at a local level (zones). In this paper, we propose a novel method for predicting the sign of the unbalance between the power produced by renewable sources and the power intake at the local level, considering zones composed of multiple power plants and with heterogeneous characteristics. The method uses a set of historical features and is based on Computational Intelligence techniques able to learn the relationship between historical data and the power unbalance in heterogeneous geographical regions. As a case study, we evaluated the proposed method using data collected by a player in the energy market over a period of seven months. In this preliminary study, we evaluated different configurations of the proposed method, achieving results considered as satisfactory by a player in the energy market.